skills/paulund/ai/ai-grill-me/Gen Agent Trust Hub

ai-grill-me

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No evidence of malicious code, data exfiltration, or unauthorized system access was found. The skill instructions are focused on user interaction and follow standard patterns.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is instructed to explore the codebase to answer questions. Evidence: Ingestion points: codebase files (SKILL.md); Boundary markers: absent; Capability inventory: local file read access; Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 07:04 AM
Security Audit — agent-trust-hub — ai-grill-me